corrected error in the demo code

README.md

@@ -58,8 +58,8 @@ Any model can provide inaccurate or incomplete information, and should be used i
 The fastest way to get started with dRAGon is through direct import in transformers:
 
     from transformers import AutoTokenizer, AutoModelForCausalLM  
-    tokenizer = AutoTokenizer.from_pretrained("dragon-mistral-7b-v0")  
-    model = AutoModelForCausalLM.from_pretrained("dragon-mistral-7b-v0")  
+    tokenizer = AutoTokenizer.from_pretrained("llmware/dragon-mistral-7b-v0")  
+    model = AutoModelForCausalLM.from_pretrained("llmware/dragon-mistral-7b-v0")  
 
 Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model.  The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.  
 
@@ -76,7 +76,6 @@ To get the best results, package "my_prompt" as follows:
 
     my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
 
-
 If you are using a HuggingFace generation script:
 
     # prepare prompt packaging used in fine-tuning process
@@ -88,14 +87,7 @@ If you are using a HuggingFace generation script:
     #   temperature: set at 0.3 for consistency of output
     #   max_new_tokens:  set at 100 - may prematurely stop a few of the summaries
 
-    outputs = model.generate(
-            inputs.input_ids.to(device),
-            eos_token_id=tokenizer.eos_token_id,
-            pad_token_id=tokenizer.eos_token_id,
-            do_sample=True,
-            temperature=0.3,
-            max_new_tokens=100,
-            )
+    
 
     output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True)